Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Slovenia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	delta
    -0.07
    safe
    -0.07
     PhD
    -0.06
     директор
    -0.06
     方
    -0.06
     카
    -0.06
     encontrar
    -0.06
     revolver
    -0.06
     Maxwell
    -0.06
     سرعت
    -0.06
    POSITIVE LOGITS
     Slovenia
    0.08
    õ
    0.07
    λά
    0.07
    conciliation
    0.06
    /lab
    0.06
     Kylie
    0.06
     Між
    0.06
    �
    0.06
    acoes
    0.06
    ществ
    0.06
    Act Density 0.013%

    No Known Activations